Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Manchester

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    2
    -0.08
    🐍
    -0.07
    _ur
    -0.07
    ခ
    -0.07
    早早
    -0.07
     enr
    -0.07
    🍥
    -0.07
    穿越
    -0.07
    经过多年
    -0.07
    💪
    -0.06
    POSITIVE LOGITS
     whites
    0.09
    ')}>↵
    0.07
     Wikimedia
    0.07
     LSTM
    0.07
    '>{
    0.07
     packs
    0.07
     thoáng
    0.07
     Scholar
    0.07
    孩子的
    0.07
     Americ
    0.06
    Act Density 0.005%

    No Known Activations